The invention provides a traffic accident prediction method based on hard parameter sharing multi-task learning. The method comprises the following steps: preprocessing traffic accident original data; processing the data of the external factors influencing the occurrence of the traffic accident to respectively obtain static factor data and dynamic factor data; extracting features of various static factor data through a multi-channel convolutional network and a compression-excitation network; extracting the characteristics of various dynamic factor data through a Transform network; performing information fusion; specific network layers are constructed according to different prediction tasks, and prediction values of the different prediction tasks are obtained in the specific network layers; constructing a joint loss function of a plurality of prediction tasks, and obtaining a prediction model by using an Adam optimizer; and obtaining prediction results of the plurality of traffic accident prediction tasks by using the prediction model. According to the invention, joint learning of a plurality of traffic accident prediction tasks is realized, a more comprehensive and clearer traffic accident prediction result is provided, and the prediction precision is improved.

    本发明提出了一种基于硬参数共享多任务学习的交通事故预测方法,其步骤如下:对交通事故原始数据进行预处理;对影响交通事故发生的外部因素的数据进行处理分别得到静态因素数据和动态因素数据;通过多通道卷积网络和压缩‑激发网络提取各种静态因素数据的特征;通过Transformer网络提取各种动态因素数据的特征;进行信息融合;根据不同的预测任务分别构建其特定的网络层,在特定的网络层得到不同预测任务的预测值;构建多个预测任务的联合损失函数,利用Adam优化器得到预测模型;利用预测模型得到多个交通事故预测任务的预测结果。本发明实现了对多个交通事故预测任务的共同学习,提供更加全面更加明确的交通事故预测结果,且提高了预测精度。


    Access

    Download


    Export, share and cite



    Title :

    Traffic accident prediction method based on hard parameter sharing multi-task learning


    Additional title:

    一种基于硬参数共享多任务学习的交通事故预测方法


    Contributors:
    ZHOU YI (author) / HOU HONGXIN (author) / WANG LI (author) / NING NIANWEN (author) / SHI HUAGUANG (author) / ZHANG YANYU (author)

    Publication date :

    2023-06-23


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Distributed multi-task machine learning for traffic prediction

    GUO JIANLIN / ZENG TENGCHAN / KIM KYEONG JIN et al. | European Patent Office | 2024

    Free access

    DISTRIBUTED MULTI-TASK MACHINE LEARNING FOR TRAFFIC PREDICTION

    GUO JIANLIN / ZENG TENGCHAN / KIM KYEONG JIN et al. | European Patent Office | 2023

    Free access

    Traffic Accident Risk Prediction Using Machine Learning

    Banerjee, Kakoli / Bali, Vikram / Sharma, Aanchal et al. | IEEE | 2022


    Traffic accident prediction method

    CHEN MING / ZHONG HUIJIAN / LIN JING et al. | European Patent Office | 2023

    Free access

    DISTRIBUTED MULTI-TASK MACHINE LEARNING FOR TRAFFIC PREDICTION

    GUO JIANLIN / ZENG TENGCHAN / KIM KYEONG JIN et al. | European Patent Office | 2023

    Free access